I'm looking at Springtail community analysis and want to see what, if any, affect Litter Type (LT), Site Type (ST), and Sampling Day (SD) have on springtail abundance. LT and ST both have 3 factors each while SD has 2.

I'm still learning the ropes with R, but initially thought the best way to do this was along the lines of:

model1 <- glm(Abundance ~ LT * ST * SD, data=mydata, family=poisson())

anova(model1, test="Chisq")

Does this seem logical? Am I on the right track? Further more I'd like to perform some sort of posthoc TUKEYHSD test to get more information on any variables which DO significantly affect Springtail Abundance. Is this possible?

  • $\begingroup$ Could you explain what "abundance" means, scientifically, and how that is measured by your response variable Abundance? $\endgroup$ – whuber Nov 5 '18 at 14:01
  • 1
    $\begingroup$ "Abundance" here is the total number of Springtails recorded in each litter trap. Each litter trap (n=102) has an abundance value of the total number of individuals counted in the trap (values range from 1 to 350) $\endgroup$ – O.Cowan Nov 5 '18 at 15:53
  • $\begingroup$ Have a look at my answers here and here. Maybe that will help you to get further. $\endgroup$ – Stefan Nov 6 '18 at 2:08

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.